On the Quantization of Cellular Neural Networks for Cyber-Physical Systems

03/05/2019
by   Xiaowei Xu, et al.
0

Cyber-Physical Systems (CPSs) have been pervasive including smart grid, autonomous automobile systems, medical monitoring, process control systems, robotics systems, and automatic pilot avionics. As usually implemented on embedded devices, CPS is typically constrained by computation capacity and energy consumption. In some CPS applications such as telemedicine and advanced driving assistance system (ADAS), data processing on the embedded devices is preferred due to security/safety and real-time requirement. Therefore, high efficiency is highly desirable for such CPS applications. In this paper we present CeNN quantization for high-efficient processing for CPS applications, particularly telemedicine and ADAS applications. We systematically put forward powers-of-two based incremental quantization of CeNNs for efficient hardware implementation. The incremental quantization contains iterative procedures including parameter partition, parameter quantization, and re-training. We propose five different strategies including random strategy, pruning inspired strategy, weighted pruning inspired strategy, nearest neighbor strategy, and weighted nearest neighbor strategy. Experimental results show that our approach can achieve a speedup up to 7.8x with no performance loss compared with the state-of-the-art FPGA solutions for CeNNs.

READ FULL TEXT

page 5

page 10

research
06/01/2023

The TeamPlay Project: Analysing and Optimising Time, Energy, and Security for Cyber-Physical Systems

Non-functional properties, such as energy, time, and security (ETS) are ...
research
02/01/2021

Intelligent Network Layer for Cyber-Physical Systems Security

Cyber-Physical System (CPS) has made a tremendous progress in recent yea...
research
10/01/2018

Data-driven Discovery of Cyber-Physical Systems

Cyber-physical systems (CPSs) embed software into the physical world. Th...
research
12/08/2018

A Multilevel Cybersecurity and Safety Monitor for Embedded Cyber-Physical Systems

Cyber-physical systems (CPS) are composed of various embedded subsystems...
research
08/23/2022

DeepPicarMicro: Applying TinyML to Autonomous Cyber Physical Systems

Running deep neural networks (DNNs) on tiny Micro-controller Units (MCUs...
research
10/07/2020

Reconfigurable Cyber-Physical System for Lifestyle Video-Monitoring via Deep Learning

Indoor monitoring of people at their homes has become a popular applicat...
research
02/02/2018

Advanced Symbolic Time Series Analysis in Cyber Physical Systems

This paper presents advanced symbolic time series analysis (ASTSA) for l...

Please sign up or login with your details

Forgot password? Click here to reset